Automated learning from data by means of deep neural networks is finding use in an ever-increasing number of applications, yet key theoretical questions about how it works remain unanswered. A physics-based approach may help to bridge this gap.
This is a preview of subscription content, access via your institution
Access options
Access Nature and 54 other Nature Portfolio journals
Get Nature+, our best-value online-access subscription
$29.99 / 30 days
cancel any time
Subscribe to this journal
Receive 12 print issues and online access
$209.00 per year
only $17.42 per issue
Buy this article
- Purchase on Springer Link
- Instant access to full article PDF
Prices may be subject to local taxes which are calculated during checkout
References
LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436 (2015).
Deep learning. Wikipedia https://go.nature.com/2XsJf4v (2020).
Zdeborová, L. Nat. Phys. 13, 420–421 (2017).
Carleo, G. et al. Rev. Mod. Phys. 91, 045002 (2019).
Vaswani, A. et al. In Advances in Neural Information Processing Systems 30 5998–6008 (NIPS, 2017).
Schmidhuber, J. Neural Netw. 61, 85–117 (2015).
Breiman, L. In The Mathematics of Generalization 11–15 (Addison-Wesley, 1995).
Blum, A. & Rivest, R. L. In Advances in Neural Information Processing Systems 494–501 (1989).
Zhang, C., Bengio, S., Hardt, M., Recht, B. & Vinyals, O. Preprint at https://arxiv.org/abs/1611.03530 (2016).
Hopeld, J. J. Proc. Natl Acad. Sci. USA 79, 2554–2558 (1982).
Amit, D. J., Gutfreund, H. & Sompolinsky, H. Phys. Rev. Lett. 55, 1530–1533 (1985).
Gardner, E. J. Phys. A 21, 257–270 (1988).
Gardner, E. & Derrida, B. J. Phys. A 21, 271–284 (1988).
Mézard, M., Parisi, G. & Virasoro, M. Spin Glass Theory and Beyond: An Introduction to the Replica Method and Its Applications Vol. 9 (World Scientific, 1987).
Hertz, J., Krogh, A. & Palmer, R. G. Introduction to the Theory of Neural Computation (Addison-Wesley, 1991).
Seung, S., Sompolinsky, H. & Tishby, N. Phys. Rev. A 45, 6056–6091 (1992).
Watkin, T. L. H., Rau, A. & Biehl, M. Rev. Mod. Phys. 65, 499–556 (1993).
Engel, A. & Van den Broeck, C. P. L. Statistical Mechanics of Learning (Cambridge Univ. Press, 2001).
Theoretical physics for deep learning. Workshop at the 36th International Conference on Machine Learning https://go.nature.com/36gSRDb (ICML, 2019).
Machine learning and the physical sciences. Workshop at the 33rd Conference on Neural Information Processing Systems https://go.nature.com/2Xd16w1 (NeurIPS, 2019).
Bahri, Y. et al. Ann. Rev. Cond. Matt. Phys. 11, 501–528 (2019).
Agliari, E. et al. (eds). Machine Learning and Statistical Physics: Theory, Inspiration, Application; J. Phys. A (IOP, 2020); https://go.nature.com/2ZlvUNN
Mezard, M. et al. (eds). Machine Learning 2019; J. Stat. Mech. (2019); https://go.nature.com/2XkTCY2
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zdeborová, L. Understanding deep learning is also a job for physicists. Nat. Phys. 16, 602–604 (2020). https://doi.org/10.1038/s41567-020-0929-2
Published:
Issue Date:
DOI: https://doi.org/10.1038/s41567-020-0929-2
This article is cited by
-
Inversion dynamics of class manifolds in deep learning reveals tradeoffs underlying generalization
Nature Machine Intelligence (2024)
-
Recent advances for quantum classifiers
Science China Physics, Mechanics & Astronomy (2022)